Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America.
PLoS One. 2022 May 9;17(5):e0267753. doi: 10.1371/journal.pone.0267753. eCollection 2022.
Deep learning segmentation requires large datasets with ground truth. Image annotation is time consuming and leads to shortages of ground truth data for clinical imaging. This study is to investigate the feasibility of kidney segmentation using deep learning convolution neural network (CNN) models trained with MR images from only a few subjects.
A total of 60 subjects from two cohorts were included in this study. The first cohort of 20 subjects from publicly available data was used for training and testing. The second cohort of 40 subjects with renal masses from our institution was used for testing only. A few-shot deep learning approach using 3D augmentation was investigated. T1-weighted images in the first cohort were used for training and testing. Cascaded CNN networks were trained using images from one, three, and six subjects, respectively. Images for the remaining subjects were used for testing. Images in the second cohort were utilized for testing only. Dice and Jaccard coefficients were generated to evaluate the performance of CNN models. Statistical analyses for segmentation metrics among different approaches were performed.
Our approach achieved mean Dice coefficients of 0.85 using a single training subject and 0.91 with six training subjects. Compared to a single Unet, the cascaded network significantly improved the results using a single training subject (Dice, 0.759 vs. 0.835; p<0.001) and three subjects (0.864 vs. 0.893; p = 0.015) in the first cohort, and the results for the second cohort (0.821 vs. 0.873; p = 0.008).
Our few-shot kidney segmentation approach using 3D augmentation achieved a good performance even using a single Unet. Furthermore, the cascaded network significantly improved the performance of segmentation and was superior to a single Unet in certain cases. Our approach provides a promising solution to segmentation in medical imaging when the number of ground truth masks is limited.
深度学习分割需要具有真实数据的大型数据集。图像标注耗时且导致临床成像的真实数据短缺。本研究旨在探讨仅使用少数受试者的磁共振图像训练深度学习卷积神经网络 (CNN) 模型进行肾脏分割的可行性。
本研究共纳入了两个队列的 60 名受试者。第一队列的 20 名受试者来自公开数据，用于训练和测试。第二队列的 40 名来自本机构的肾肿瘤患者仅用于测试。研究了一种使用 3D 增强的少量样本深度学习方法。第一队列的 T1 加权图像用于训练和测试。分别使用来自一个、三个和六个受试者的图像训练级联 CNN 网络。其余受试者的图像用于测试。第二队列的图像仅用于测试。生成 Dice 和 Jaccard 系数以评估 CNN 模型的性能。对不同方法的分割指标进行了统计分析。
我们的方法使用单个训练对象实现了 0.85 的平均 Dice 系数，使用六个训练对象实现了 0.91 的平均 Dice 系数。与单个 Unet 相比，级联网络显著提高了使用单个训练对象（Dice，0.759 与 0.835；p<0.001）和三个训练对象（0.864 与 0.893；p = 0.015）的第一队列的结果，以及第二队列的结果（0.821 与 0.873；p = 0.008）。
即使使用单个 Unet，我们的 3D 增强少量样本肾脏分割方法也能获得良好的性能。此外，级联网络显著提高了分割性能，在某些情况下优于单个 Unet。当真实数据数量有限时，我们的方法为医学成像中的分割提供了一种有前途的解决方案。
